Upload imatrix.log with huggingface_hub

imatrix.log

@@ -0,0 +1,126 @@
+build: 3825 (1e436302) with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
+llama_model_loader: loaded meta data with 30 key-value pairs and 148 tensors from Llama-Guard-3-1B-IMat-GGUF/Llama-Guard-3-1B.Q8_0.gguf.hardlink.gguf (version GGUF V3 (latest))
+llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
+llama_model_loader: - kv   0:                       general.architecture str              = llama
+llama_model_loader: - kv   1:                               general.type str              = model
+llama_model_loader: - kv   2:                               general.name str              = Llama Guard 3 1B
+llama_model_loader: - kv   3:                           general.basename str              = Llama-Guard-3
+llama_model_loader: - kv   4:                         general.size_label str              = 1B
+llama_model_loader: - kv   5:                            general.license str              = llama3.2
+llama_model_loader: - kv   6:                               general.tags arr[str,6]       = ["facebook", "meta", "pytorch", "llam...
+llama_model_loader: - kv   7:                          general.languages arr[str,8]       = ["en", "de", "fr", "it", "pt", "hi", ...
+llama_model_loader: - kv   8:                          llama.block_count u32              = 16
+llama_model_loader: - kv   9:                       llama.context_length u32              = 131072
+llama_model_loader: - kv  10:                     llama.embedding_length u32              = 2048
+llama_model_loader: - kv  11:                  llama.feed_forward_length u32              = 8192
+llama_model_loader: - kv  12:                 llama.attention.head_count u32              = 32
+llama_model_loader: - kv  13:              llama.attention.head_count_kv u32              = 8
+llama_model_loader: - kv  14:                       llama.rope.freq_base f32              = 500000.000000
+llama_model_loader: - kv  15:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
+llama_model_loader: - kv  16:                 llama.attention.key_length u32              = 64
+llama_model_loader: - kv  17:               llama.attention.value_length u32              = 64
+llama_model_loader: - kv  18:                          general.file_type u32              = 7
+llama_model_loader: - kv  19:                           llama.vocab_size u32              = 128256
+llama_model_loader: - kv  20:                 llama.rope.dimension_count u32              = 64
+llama_model_loader: - kv  21:                       tokenizer.ggml.model str              = gpt2
+llama_model_loader: - kv  22:                         tokenizer.ggml.pre str              = llama-bpe
+llama_model_loader: - kv  23:                      tokenizer.ggml.tokens arr[str,128256]  = ["!", "\"", "#", "$", "%", "&", "'", ...
+llama_model_loader: - kv  24:                  tokenizer.ggml.token_type arr[i32,128256]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
+llama_model_loader: - kv  25:                      tokenizer.ggml.merges arr[str,280147]  = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
+llama_model_loader: - kv  26:                tokenizer.ggml.bos_token_id u32              = 128000
+llama_model_loader: - kv  27:                tokenizer.ggml.eos_token_id u32              = 128009
+llama_model_loader: - kv  28:                    tokenizer.chat_template str              = {%- if messages|length % 2 == 0 -%}\n ...
+llama_model_loader: - kv  29:               general.quantization_version u32              = 2
+llama_model_loader: - type  f32:   34 tensors
+llama_model_loader: - type q8_0:  114 tensors
+llm_load_vocab: special tokens cache size = 256
+llm_load_vocab: token to piece cache size = 0.7999 MB
+llm_load_print_meta: format           = GGUF V3 (latest)
+llm_load_print_meta: arch             = llama
+llm_load_print_meta: vocab type       = BPE
+llm_load_print_meta: n_vocab          = 128256
+llm_load_print_meta: n_merges         = 280147
+llm_load_print_meta: vocab_only       = 0
+llm_load_print_meta: n_ctx_train      = 131072
+llm_load_print_meta: n_embd           = 2048
+llm_load_print_meta: n_layer          = 16
+llm_load_print_meta: n_head           = 32
+llm_load_print_meta: n_head_kv        = 8
+llm_load_print_meta: n_rot            = 64
+llm_load_print_meta: n_swa            = 0
+llm_load_print_meta: n_embd_head_k    = 64
+llm_load_print_meta: n_embd_head_v    = 64
+llm_load_print_meta: n_gqa            = 4
+llm_load_print_meta: n_embd_k_gqa     = 512
+llm_load_print_meta: n_embd_v_gqa     = 512
+llm_load_print_meta: f_norm_eps       = 0.0e+00
+llm_load_print_meta: f_norm_rms_eps   = 1.0e-05
+llm_load_print_meta: f_clamp_kqv      = 0.0e+00
+llm_load_print_meta: f_max_alibi_bias = 0.0e+00
+llm_load_print_meta: f_logit_scale    = 0.0e+00
+llm_load_print_meta: n_ff             = 8192
+llm_load_print_meta: n_expert         = 0
+llm_load_print_meta: n_expert_used    = 0
+llm_load_print_meta: causal attn      = 1
+llm_load_print_meta: pooling type     = 0
+llm_load_print_meta: rope type        = 0
+llm_load_print_meta: rope scaling     = linear
+llm_load_print_meta: freq_base_train  = 500000.0
+llm_load_print_meta: freq_scale_train = 1
+llm_load_print_meta: n_ctx_orig_yarn  = 131072
+llm_load_print_meta: rope_finetuned   = unknown
+llm_load_print_meta: ssm_d_conv       = 0
+llm_load_print_meta: ssm_d_inner      = 0
+llm_load_print_meta: ssm_d_state      = 0
+llm_load_print_meta: ssm_dt_rank      = 0
+llm_load_print_meta: ssm_dt_b_c_rms   = 0
+llm_load_print_meta: model type       = ?B
+llm_load_print_meta: model ftype      = Q8_0
+llm_load_print_meta: model params     = 1.50 B
+llm_load_print_meta: model size       = 1.48 GiB (8.50 BPW) 
+llm_load_print_meta: general.name     = Llama Guard 3 1B
+llm_load_print_meta: BOS token        = 128000 '<|begin_of_text|>'
+llm_load_print_meta: EOS token        = 128009 '<|eot_id|>'
+llm_load_print_meta: LF token         = 128 'Ä'
+llm_load_print_meta: EOT token        = 128009 '<|eot_id|>'
+llm_load_print_meta: EOM token        = 128008 '<|eom_id|>'
+llm_load_print_meta: EOG token        = 128008 '<|eom_id|>'
+llm_load_print_meta: EOG token        = 128009 '<|eot_id|>'
+llm_load_print_meta: max token length = 256
+ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
+ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
+ggml_cuda_init: found 1 CUDA devices:
+  Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes
+llm_load_tensors: ggml ctx size =    0.14 MiB
+llm_load_tensors: offloading 16 repeating layers to GPU
+llm_load_tensors: offloading non-repeating layers to GPU
+llm_load_tensors: offloaded 17/17 layers to GPU
+llm_load_tensors:        CPU buffer size =   266.16 MiB
+llm_load_tensors:      CUDA0 buffer size =  1252.42 MiB
+.............................................................
+llama_new_context_with_model: n_ctx      = 512
+llama_new_context_with_model: n_batch    = 512
+llama_new_context_with_model: n_ubatch   = 512
+llama_new_context_with_model: flash_attn = 0
+llama_new_context_with_model: freq_base  = 500000.0
+llama_new_context_with_model: freq_scale = 1
+llama_kv_cache_init:      CUDA0 KV buffer size =    16.00 MiB
+llama_new_context_with_model: KV self size  =   16.00 MiB, K (f16):    8.00 MiB, V (f16):    8.00 MiB
+llama_new_context_with_model:  CUDA_Host  output buffer size =     0.49 MiB
+llama_new_context_with_model:      CUDA0 compute buffer size =   254.50 MiB
+llama_new_context_with_model:  CUDA_Host compute buffer size =     5.01 MiB
+llama_new_context_with_model: graph nodes  = 518
+llama_new_context_with_model: graph splits = 2
+
+system_info: n_threads = 25 (n_threads_batch = 25) / 32 | AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 1 | AVX512_VBMI = 1 | AVX512_VNNI = 1 | AVX512_BF16 = 1 | FMA = 1 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | RISCV_VECT = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | 
+compute_imatrix: tokenizing the input ..
+compute_imatrix: tokenization took 41.7 ms
+compute_imatrix: computing over 125 chunks with batch_size 512
+compute_imatrix: 0.26 seconds per pass - ETA 0.53 minutes
+[1]12.6981,[2]11.2023,[3]10.1980,[4]12.5026,[5]13.2416,[6]11.1191,[7]11.6862,[8]12.6711,[9]12.3544,[10]11.0861,[11]11.9575,[12]13.0696,[13]13.7919,[14]14.3594,[15]14.8069,[16]15.3642,[17]15.5152,[18]15.0535,[19]14.2616,[20]14.0102,[21]14.2288,[22]14.3777,[23]14.9627,[24]15.2010,[25]15.7363,[26]15.6310,[27]15.7498,[28]16.2149,[29]16.2048,[30]15.9883,[31]14.9849,[32]14.4200,[33]14.0878,[34]13.7783,[35]13.9568,[36]14.1931,[37]14.0283,[38]14.0189,[39]14.3262,[40]14.4825,[41]14.8521,[42]15.2848,[43]15.7827,[44]16.1563,[45]16.6374,[46]16.3597,[47]16.5542,[48]16.6284,[49]16.7525,[50]16.5988,[51]16.8583,[52]17.0215,[53]17.2505,[54]17.4594,[55]17.6825,[56]17.7626,[57]17.9108,[58]17.9600,[59]18.2017,[60]18.0045,[61]17.8883,[62]18.0668,[63]18.0690,[64]17.8717,[65]17.8126,[66]17.7703,[67]17.7398,[68]17.7826,[69]17.7080,[70]17.6097,[71]17.5217,[72]17.5573,[73]17.5261,[74]17.4918,[75]17.4773,[76]17.5200,[77]17.4191,[78]17.4381,[79]17.4517,[80]17.4695,[81]17.3574,[82]17.3725,[83]17.3748,[84]17.1655,[85]17.1321,[86]17.1689,[87]17.1813,[88]17.2473,[89]17.3173,[90]17.1617,[91]17.0510,[92]16.9346,[93]16.8425,[94]16.7132,[95]16.6337,[96]16.5423,[97]16.5106,[98]16.5533,[99]16.6885,[100]16.8052,[101]16.9002,[102]17.1638,[103]17.1933,[104]17.2173,[105]17.1397,[106]17.1190,[107]17.1367,[108]17.1499,[109]17.1273,[110]17.2097,[111]17.2813,[112]17.2230,[113]17.1821,[114]17.2224,[115]17.2968,[116]17.2962,[117]17.2898,[118]17.3580,[119]17.2641,[120]17.3443,[121]17.4507,[122]17.5163,[123]17.6180,[124]17.7018,[125]17.8182,
+Final estimate: PPL = 17.8182 +/- 0.29274
+
+llama_perf_context_print:        load time =     924.47 ms
+llama_perf_context_print: prompt eval time =   18281.11 ms / 64000 tokens (    0.29 ms per token,  3500.88 tokens per second)
+llama_perf_context_print:        eval time =       0.00 ms /     1 runs   (    0.00 ms per token,      inf tokens per second)
+llama_perf_context_print:       total time =   19801.33 ms / 64001 tokens